def run_weather_online(interpreter,
domain_file='weather_domain.yml',
training_data_file='data/stories.md'):
action_endpoint = EndpointConfig(url="http://localhost:5000/webhook")
fallback = FallbackPolicy(fallback_action_name="action_default_fallback",
core_threshold=0.8,
nlu_threshold=0.8)
agent = Agent('./weather_domain.yml',
policies=[
MemoizationPolicy(max_history=2, ),
KerasPolicy(epochs=500,
batch_size=50,
validation_split=0.2), fallback
],
interpreter=interpreter,
action_endpoint=action_endpoint)
data_ = agent.load_data(training_data_file, augmentation_factor=50)
agent.train(data_)
interactive.run_interactive_learning(agent,
training_data_file,
skip_visualization=True)
# agent.handle_channels(input_channel)
return agent
def run_online_dialogue(serve_forever=True):
interpreter = RasaNLUInterpreter('./models/nlu/default/chat')
action_endpoint = EndpointConfig(url="http://localhost:5004/webhook")
agent = Agent.load('./models/dialogue',
interpreter=interpreter,
action_endpoint=action_endpoint)
interactive.run_interactive_learning(agent) #, channel='cmdline')
return agent
def run_mental_bot(serve_forever=True):
interpreter = RasaNLUInterpreter('./models/nlu/default/mentalnlu')
agent = Agent.load('./models/dialogue', interpreter=interpreter)
training_data_file = 'data/stories.md'
if serve_forever:
interactive.run_interactive_learning(agent, training_data_file)
return agent
def run_weather_online(interpreter,
domain_file="weather_domain.yml",
training_data_file='data/stories.md'):
policies2 = policy_config.load("config.yml")
action_endpoint = "endpoint.yml"
agent = Agent(domain_file,policies=policies2,interpreter=interpreter,action_endpoint=action_endpoint)
data = asyncio.run(agent.load_data(training_data_file))
agent.train(data)
interactive.run_interactive_learning(agent,training_data_file)
return agent
def do_interactive_learning(cmdline_args, stories, additional_arguments=None):
from rasa_core.training import interactive
if cmdline_args.cors and cmdline_args.finetune:
raise ValueError("--core can only be used without " "--finetune flag.")
interactive.run_interactive_learning(
stories,
finetune=cmdline_args.finetune,
skip_visualization=cmdline_args.skip_visualization,
server_args=cmdline_args.__dict__,
additional_arguments=additional_arguments)
def train_agent(input_channel, nlu_interpreter,
domain_file="domain.yml",
training_data_file='./data/dialogue/stories.md'):
#endpoints = "endpoints.yml"
agent = Agent(domain_file,
policies=[MemoizationPolicy(max_history=2), KerasPolicy()],
interpreter=nlu_interpreter)
data = agent.load_data(training_data_file)
agent.train(data, input_channel=input_channel, batch_size=50, epochs=200, max_training_samples=300)
agent = Agent.load('models/dialogue/default/dialogue_model', interpreter = nlu_interpreter, action_endpoint=EndpointConfig(url = "http://localhost:5055/webhook"))
interactive.run_interactive_learning(agent, training_data_file)
return agent
def run_mental_online(interpreter,
domain_file="mental_domain.yml",
training_data_file='data/stories.md'):
action_endpoint = EndpointConfig(url="http://localhost:5055/webhook")
agent = Agent(domain_file,
policies=[
MemoizationPolicy(max_history=2),
KerasPolicy(max_history=4, epochs=1000, batch_size=50)
],
interpreter=interpreter,
action_endpoint=action_endpoint)
data = agent.load_data(training_data_file)
agent.train(data)
interactive.run_interactive_learning(agent, training_data_file)
return agent
def train_agent(interpreter,
domain_file="domain.yml",
training_file='data/stories.md'):
action_endpoint = EndpointConfig('http://localhost:5055/webhook')
policies = [MemoizationPolicy(max_history=3),
KerasPolicy(max_history=3, epochs=10, batch_size=10)]
agent = Agent(domain_file, policies=policies,
interpreter=interpreter,
action_endpoint=action_endpoint)
stories = agent.load_data(training_file)
agent.train(stories)
interactive.run_interactive_learning(agent, training_file)
return agent
def run_restaurant_online(interpreter,
domain_file='restaurant_domain.yml',
training_data_file='data/stories.md'):
action_endpoint = EndpointConfig(url="http://localhost:5055/webhook")
agent = Agent(domain_file,
policies=[MemoizationPolicy(),
KerasPolicy()],
interpreter=interpreter,
action_endpoint=action_endpoint)
training_data = agent.load_data(training_data_file)
agent.train(training_data,
batch_size=50,
epochs=200,
max_training_samples=300)
interactive.run_interactive_learning(agent)
return agent
def run_weather_online(
interpreter,
domain_file="/home/saradindu/dev/Work-II/Happsales/assistant_domain.yml",
training_data_file='/home/saradindu/dev/Work-II/Happsales/data/stories.md'
):
action_endpoint = EndpointConfig(url="http://localhost:5055/webhook")
agent = Agent(domain_file,
policies=[
MemoizationPolicy(max_history=2),
KerasPolicy(max_history=3, epochs=3, batch_size=50)
],
interpreter=interpreter,
action_endpoint=action_endpoint)
data = agent.load_data(training_data_file)
agent.train(data)
interactive.run_interactive_learning(agent, training_data_file)
return agent
def run_weather_online(input_channel,
interpreter,
domain_file="weather_domain.yml",
training_data_file='data/stories.md'):
#policies2 = policy_config.load("config.yml")
action_endpoints = EndpointConfig(url="http://localhost:5055/webhook")
agent = Agent(
"weather_domain.yml",
interpreter=interpreter,
policies=[MemoizationPolicy(),
KerasPolicy(epochs=200, batch_size=50)],
action_endpoint=action_endpoints)
#data = asyncio.run(agent.load_data(training_data_file))
data = agent.load_data(training_data_file)
agent.train(data)
interactive.run_interactive_learning(agent, training_data_file)
return agent
def do_interactive_learning(cmdline_args, stories, additional_arguments):
_endpoints = AvailableEndpoints.read_endpoints(cmdline_args.endpoints)
_interpreter = NaturalLanguageInterpreter.create(cmdline_args.nlu,
_endpoints.nlu)
if cmdline_args.core:
if cmdline_args.finetune:
raise ValueError("--core can only be used without "
"--finetune flag.")
logger.info("Loading a pre-trained model. This means that "
"all training-related parameters will be ignored.")
_broker = PikaProducer.from_endpoint_config(_endpoints.event_broker)
_tracker_store = TrackerStore.find_tracker_store(
None, _endpoints.tracker_store, _broker)
_agent = Agent.load(cmdline_args.core,
interpreter=_interpreter,
generator=_endpoints.nlg,
tracker_store=_tracker_store,
action_endpoint=_endpoints.action)
else:
if cmdline_args.out:
model_directory = cmdline_args.out
else:
model_directory = tempfile.mkdtemp(suffix="_core_model")
_agent = train_dialogue_model(cmdline_args.domain, stories,
model_directory, _interpreter,
_endpoints, cmdline_args.dump_stories,
cmdline_args.config[0], None,
additional_arguments)
interactive.run_interactive_learning(
_agent,
stories,
finetune=cmdline_args.finetune,
skip_visualization=cmdline_args.skip_visualization)
def do_interactive_learning(cmdline_args, stories, additional_arguments):
_endpoints = AvailableEndpoints.read_endpoints(cmdline_args.endpoints)
_interpreter = NaturalLanguageInterpreter.create(cmdline_args.nlu,
_endpoints.nlu)
if (isinstance(cmdline_args.config, list)
and len(cmdline_args.config) > 1):
raise ValueError("You can only pass one config file at a time")
if cmdline_args.core and cmdline_args.finetune:
raise ValueError("--core can only be used without --finetune flag.")
elif cmdline_args.core:
logger.info("loading a pre-trained model. "
"all training-related parameters will be ignored")
_broker = PikaProducer.from_endpoint_config(_endpoints.event_broker)
_tracker_store = TrackerStore.find_tracker_store(
None, _endpoints.tracker_store, _broker)
_agent = Agent.load(cmdline_args.core,
interpreter=_interpreter,
generator=_endpoints.nlg,
tracker_store=_tracker_store,
action_endpoint=_endpoints.action)
else:
if not cmdline_args.out:
raise ValueError("you must provide a path where the model "
"will be saved using -o / --out")
_agent = train_dialogue_model(cmdline_args.domain, stories,
cmdline_args.out, _interpreter,
_endpoints, cmdline_args.dump_stories,
cmdline_args.config[0], None,
additional_arguments)
interactive.run_interactive_learning(
_agent,
stories,
finetune=cmdline_args.finetune,
skip_visualization=cmdline_args.skip_visualization)
raise ValueError("--core can only be used together with the"
"--interactive flag.")
elif cmdline_args.finetune:
raise ValueError("--core can only be used together with the"
"--interactive flag and without --finetune flag.")
else:
logger.info("loading a pre-trained model. ",
"all training-related parameters will be ignored")
_agent = Agent.load(cmdline_args.core,
interpreter=_interpreter,
generator=_endpoints.nlg,
tracker_store=_tracker_store,
action_endpoint=_endpoints.action)
else:
if not cmdline_args.out:
raise ValueError("you must provide a path where the model "
"will be saved using -o / --out")
_agent = train_dialogue_model(cmdline_args.domain, stories,
cmdline_args.out, _interpreter,
_endpoints, cmdline_args.history,
cmdline_args.dump_stories,
cmdline_args.config,
additional_arguments)
if cmdline_args.interactive:
interactive.run_interactive_learning(
_agent,
stories,
finetune=cmdline_args.finetune,
skip_visualization=cmdline_args.skip_visualization)
import asyncio
import logging
import rasa.utils
from rasa_core import utils
from rasa_core.training import interactive
logger = logging.getLogger(__name__)
if __name__ == '__main__':
rasa.utils.configure_colored_logging(loglevel="INFO")
loop = asyncio.get_event_loop()
logger.info("This example does not include NLU data."
"Please specify the desired intent with a preceding '/', e.g."
"'/greet' .")
loop.run_until_complete(
interactive.run_interactive_learning("data/stories.md",
server_args={
"domain": "domain.yml",
"out": "models/dialogue",
"stories": "data/stories.md",
"config": ['config.yml']
}))
def train_interactive(self):
self.train_nlu()
self.agent = self.train_dialogue()
return interactive.run_interactive_learning(self.agent)
import logging from rasa_core import utils, train from rasa_core.training import interactive logger = logging.getLogger(__name__) def train_agent(): return train.train_dialogue_model(domain_file = 'weather_domain.yml', stories_file = './data/stories.md', output_path = './models/dialogue', policy_config = 'policy_config.yml' ) if __name__ == '__main__': utils.configure_colored_logging(loglevel = "INFO") agent = train_agent() interactive.run_interactive_learning(agent = agent, stories = './data/stories.md')
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals
import logging
from rasa_core import utils, train, run
from rasa_core.training import interactive
logger = logging.getLogger(__name__)
def train_agent():
return train.train_dialogue_model(domain_file="./domain.yml",
stories_file="./data/dialogue/stories.md",
output_path="./models/dialogue/",
policy_config="./policies.yml"
)
if __name__ == '__main__':
utils.configure_colored_logging(loglevel="INFO")
agent = train_agent()
interactive.run_interactive_learning(agent, "./data/dialogue/stories.md")
import logging
from rasa_core import utils, train
from rasa_core.training import interactive
logger = logging.getLogger(__name__)
def train_agent():
return train.train_dialogue_model(domain_file="domain.yml",
stories_file="data/stories.md",
output_path="models/dialogue",
kwargs={"batch_size": 50,
"epochs": 200,
"max_training_samples": 300
})
if __name__ == '__main__':
utils.configure_colored_logging(loglevel="INFO")
agent = train_agent()
interactive.run_interactive_learning(agent)
if cmdline_args.core:
if not cmdline_args.interactive:
raise ValueError("--core can only be used together with the"
"--interactive flag.")
elif cmdline_args.finetune:
raise ValueError("--core can only be used together with the"
"--interactive flag and without --finetune flag.")
else:
logger.info("loading a pre-trained model. ",
"all training-related parameters will be ignored")
_agent = Agent.load(cmdline_args.core,
interpreter=_interpreter,
generator=_endpoints.nlg,
action_endpoint=_endpoints.action)
else:
if not cmdline_args.out:
raise ValueError("you must provide a path where the model "
"will be saved using -o / --out")
_agent = train_dialogue_model(cmdline_args.domain,
stories,
cmdline_args.out,
_interpreter,
_endpoints,
cmdline_args.history,
cmdline_args.dump_stories,
additional_arguments)
if cmdline_args.interactive:
interactive.run_interactive_learning(_agent, finetune=cmdline_args.finetune)
